Search

Abstract Free-text analysis using machine learning (ML)-based natural language processing (NLP) shows promise for diagnosing psychiatric conditions. Chat Generative Pre-trained Transformer (ChatGPT) has demonstrated preliminary initial feasibility for this purpose; however, whether it can accurately assess mental illness remains to be determined. This study evaluates the effectiveness of ChatGPT and the text-embedding-ada-002 (ADA) model in detecting post-traumatic stress disorder following childbirth (CB-PTSD), a maternal postpartum mental illness affecting millions of women annually, with no standard screening protocol. Using a sample of 1295 women who gave birth in the last six months and were 18+ years old, recruited through hospital announcements, social media, and professional organizations, we explore ChatGPT’s and ADA’s potential to screen for CB-PTSD by analyzing maternal childbirth narratives. The PTSD Checklist for DSM-5 (PCL-5; cutoff 31) was used to assess CB-PTSD. By developing an ML model that utilizes numerical vector representation of the ADA model, we identify CB-PTSD via narrative classification. Our model outperformed (F1 score: 0.81) ChatGPT and six previously published large text-embedding models trained on mental health or clinical domains data, suggesting that the ADA model can be harnessed to identify CB-PTSD. Our modeling approach could be generalized to assess other mental health disorders.

Abstract Collective attention and memory involving significant events can be quantitatively studied via social media data. Previous studies analyzed user attention to discrete events that do not change post-event, and assume universal public attention patterns. However, dynamic events with ongoing updates are common, yielding varied individual attention patterns. We explore memory of U.S. companies filing Chapter 11 bankruptcy and being mentioned on X (formerly Twitter). Unlike discrete events, Chapter 11 entails ongoing financial changes as the company typically remains operational, influencing post-event attention dynamics. We collected 248,936 X mentions for 74 companies before and after each bankruptcy. Attention surged after bankruptcy, with distinct Low and High persistence levels compared with pre-bankruptcy attention. The two tweeting patterns were modeled using biexponential models, successfully predicting (F1-score: 0.81) post-bankruptcy attention persistence. Studying bankruptcy events on social media reveals diverse attention patterns, demonstrates how pre-bankruptcy attention affects post-bankruptcy recollection, and provides insights into memory of dynamic events.

Publicly available RNA-seq data is provided mostly in raw form, resulting in a barrier for integrative analyses. Here, Lachmann et al. develop a high-throughput processing infrastructure and search database (ARCHS4) that provides processed RNA-seq data for 187,946 publicly available mouse and human samples to support exploration and reuse.

A wealth of gene expression data is publicly available, yet is little use without additional human curation. Ma’ayan and colleagues report a crowdsourcing project involving over 70 participants to annotate and analyse thousands of human disease-related gene expression datasets.